Data-driven Coreference-based Ontology Building

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ashury-Tahan, Shir, Cohen, Amir David Nissan, Cohen, Nadav, Louzoun, Yoram, Goldberg, Yoav
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910660927946752
author Ashury-Tahan, Shir
Cohen, Amir David Nissan
Cohen, Nadav
Louzoun, Yoram
Goldberg, Yoav
author_facet Ashury-Tahan, Shir
Cohen, Amir David Nissan
Cohen, Nadav
Louzoun, Yoram
Goldberg, Yoav
contents While coreference resolution is traditionally used as a component in individual document understanding, in this work we take a more global view and explore what can we learn about a domain from the set of all document-level coreference relations that are present in a large corpus. We derive coreference chains from a corpus of 30 million biomedical abstracts and construct a graph based on the string phrases within these chains, establishing connections between phrases if they co-occur within the same coreference chain. We then use the graph structure and the betweeness centrality measure to distinguish between edges denoting hierarchy, identity and noise, assign directionality to edges denoting hierarchy, and split nodes (strings) that correspond to multiple distinct concepts. The result is a rich, data-driven ontology over concepts in the biomedical domain, parts of which overlaps significantly with human-authored ontologies. We release the coreference chains and resulting ontology under a creative-commons license, along with the code.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17051
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data-driven Coreference-based Ontology Building
Ashury-Tahan, Shir
Cohen, Amir David Nissan
Cohen, Nadav
Louzoun, Yoram
Goldberg, Yoav
Computation and Language
While coreference resolution is traditionally used as a component in individual document understanding, in this work we take a more global view and explore what can we learn about a domain from the set of all document-level coreference relations that are present in a large corpus. We derive coreference chains from a corpus of 30 million biomedical abstracts and construct a graph based on the string phrases within these chains, establishing connections between phrases if they co-occur within the same coreference chain. We then use the graph structure and the betweeness centrality measure to distinguish between edges denoting hierarchy, identity and noise, assign directionality to edges denoting hierarchy, and split nodes (strings) that correspond to multiple distinct concepts. The result is a rich, data-driven ontology over concepts in the biomedical domain, parts of which overlaps significantly with human-authored ontologies. We release the coreference chains and resulting ontology under a creative-commons license, along with the code.
title Data-driven Coreference-based Ontology Building
topic Computation and Language
url https://arxiv.org/abs/2410.17051